© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 15213
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals, titles, and associations within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.02
    2:0.03
    3:0.03
    4:0.05
    5:0.44
    6:0.02
    7:0.03
    8:0.04
    9:0.18
    10:0.02
    11:0.06
    Negative Logits
    Suddenly
    -3.23
    Eventually
    -3.01
     Slowly
    -2.98
     Suddenly
    -2.96
    before
    -2.92
    enough
    -2.86
    Laughs
    -2.86
    Enough
    -2.73
    successfully
    -2.64
    pite
    -2.58
    POSITIVE LOGITS
     see
    4.52
     please
    3.66
     consult
    3.50
     check
    3.17
     click
    3.15
     beware
    3.14
     look
    3.08
     feel
    3.01
     refer
    2.90
     except
    2.90
    Activations Density 0.197%

    No Known Activations